{"id":"https://openalex.org/W4403577501","doi":"https://doi.org/10.1145/3627673.3679594","title":"Towards Deconfounded Visual Question Answering via Dual-causal Intervention","display_name":"Towards Deconfounded Visual Question Answering via Dual-causal Intervention","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577501","doi":"https://doi.org/10.1145/3627673.3679594"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066682332","display_name":"Daowan Peng","orcid":"https://orcid.org/0000-0001-5208-3811"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Daowan Peng","raw_affiliation_strings":["CCIIP Lab, School of Computer Science and Technology, Huazhong University of Science and Technology Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), Wuhan, China"],"affiliations":[{"raw_affiliation_string":"CCIIP Lab, School of Computer Science and Technology, Huazhong University of Science and Technology Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323842","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0003-4488-0102"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["CCIIP Lab, School of Computer Science and Technology, Huazhong University of Science and Technology Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), Wuhan, China"],"affiliations":[{"raw_affiliation_string":"CCIIP Lab, School of Computer Science and Technology, Huazhong University of Science and Technology Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066682332"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55221594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1867","last_page":"1877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7989450693130493},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7003008127212524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6122743487358093},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.4636244773864746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3542364835739136},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34752827882766724},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3276975154876709},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22791576385498047},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1204552948474884},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06391555070877075}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7989450693130493},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7003008127212524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6122743487358093},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.4636244773864746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3542364835739136},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34752827882766724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3276975154876709},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22791576385498047},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1204552948474884},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06391555070877075},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1485713711","https://openalex.org/W1933349210","https://openalex.org/W2064790857","https://openalex.org/W2103154136","https://openalex.org/W2143117649","https://openalex.org/W2489487449","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2962787423","https://openalex.org/W2963349562","https://openalex.org/W2963518342","https://openalex.org/W2963644680","https://openalex.org/W2963954913","https://openalex.org/W2970231061","https://openalex.org/W2978477568","https://openalex.org/W2997072136","https://openalex.org/W3016970897","https://openalex.org/W3023742835","https://openalex.org/W3034287395","https://openalex.org/W3035517717","https://openalex.org/W3035561630","https://openalex.org/W3035651653","https://openalex.org/W3096831136","https://openalex.org/W3099884329","https://openalex.org/W3103934428","https://openalex.org/W3104788521","https://openalex.org/W3110575265","https://openalex.org/W3135890226","https://openalex.org/W3154781046","https://openalex.org/W3167814535","https://openalex.org/W3171353004","https://openalex.org/W3174366544","https://openalex.org/W3175294706","https://openalex.org/W3177934633","https://openalex.org/W3199231060","https://openalex.org/W3201957104","https://openalex.org/W3202778561","https://openalex.org/W3204924011","https://openalex.org/W3216470601","https://openalex.org/W4200475325","https://openalex.org/W4213057961","https://openalex.org/W4247950230","https://openalex.org/W4283796213","https://openalex.org/W4285199586","https://openalex.org/W4285414077","https://openalex.org/W4285605365","https://openalex.org/W4286696412","https://openalex.org/W4312232840","https://openalex.org/W4312341105","https://openalex.org/W4312457137","https://openalex.org/W4320003009","https://openalex.org/W4379929708","https://openalex.org/W4383200124","https://openalex.org/W4385571123","https://openalex.org/W4385571918","https://openalex.org/W4385572018","https://openalex.org/W4385573412","https://openalex.org/W4385574188","https://openalex.org/W4385768191","https://openalex.org/W4387968117","https://openalex.org/W4393160564"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"The":[0,27,213],"Visual":[1],"Question":[2],"Answering":[3],"(VQA)":[4],"task":[5],"has":[6],"recently":[7],"become":[8],"notorious":[9],"because":[10],"models":[11,35,138,208],"are":[12,200],"prone":[13],"to":[14,79,86,89,135,160,175,202],"predicting":[15],"well-educated":[16],"\"guesses\"":[17],"as":[18,130],"answers":[19],"rather":[20,103],"than":[21,104],"deriving":[22],"them":[23,113],"through":[24],"visual":[25,150,183],"understanding.":[26],"main":[28],"culprit":[29],"for":[30,116],"this":[31,73],"is":[32],"that":[33],"VQA":[34,137,207],"memorize":[36],"the":[37,41,44,59,62,98,110,163,168,177,182,204,217,226,232,241,247,250,257],"shortcut":[38,69,122,211],"biases":[39,70],"in":[40,61,109,167,181],"dataset":[42],"during":[43],"training":[45],"process.":[46],"While":[47],"a":[48,126],"variety":[49],"of":[50,68,82,165,179,206,219,240,249,256],"solutions":[51],"have":[52],"been":[53],"proposed,":[54],"they":[55],"solely":[56],"focus":[57],"on":[58,189,231,253],"shortcuts":[60,83],"language":[63,169],"modality,":[64],"leaving":[65],"other":[66],"kinds":[67,81],"untouched.":[71],"In":[72],"paper,":[74],"we":[75,124,156],"shift":[76],"our":[77,220,223],"lens":[78],"all":[80,236,254],"and":[84,149,171,197,235,244],"resort":[85],"causal":[87,99],"inference":[88,94],"circumvent":[90],"these":[91,121],"issues.":[92],"Causal":[93,132],"methods":[95,230,252],"can":[96],"discover":[97],"effect":[100],"(P(Y|do(X)))":[101],"[27]":[102],"statistic-based":[105],"spurious":[106],"correlations":[107],"(P(Y|X))":[108],"dataset,":[111,243],"making":[112],"naturally":[114],"suitable":[115],"debiasing":[117,229],"learning.":[118],"To":[119,153],"deconfound":[120],"biases,":[123],"propose":[125],"causality-aware":[127],"method,":[128],"coined":[129],"Dual":[131],"Intervention":[133],"(DCI),":[134],"endow":[136],"with":[139],"better":[140],"generalization":[141],"by":[142],"combining":[143],"two":[144,190],"components:":[145],"linguistic":[146],"backdoor":[147,158],"intervention":[148,159,174],"front-door":[151,173],"intervention.":[152],"be":[154],"specific,":[155],"harness":[157],"cut":[161],"off":[162],"effects":[164],"confounders":[166,180],"modality":[170],"employ":[172],"eliminate":[176],"impact":[178],"modality.":[184],"We":[185],"conducted":[186],"extensive":[187],"experiments":[188],"challenging":[191],"Out-of-Distribution":[192],"(OOD)":[193],"benchmarks,":[194],"including":[195],"VQA-VS":[196,242],"VQA-CE,":[198],"which":[199],"designed":[201],"assess":[203],"robustness":[205],"under":[209],"different":[210],"biases.":[212],"experimental":[214],"results":[215],"show":[216],"effectiveness":[218],"method.":[221],"Specifically,":[222],"approach":[224],"outperforms":[225],"current":[227],"state-of-the-art":[228],"IID":[233],"metric":[234],"nine":[237],"OOD":[238],"metrics":[239,255],"also":[245],"surpasses":[246],"performance":[248],"best-performing":[251],"VQA-CE":[258],"dataset.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}